# Averaging quarterly level data to the annual level

Cross Validated Asked on January 3, 2022

From the Quarterly Workforce Indicators, I have obtained a measure of data measured at the quarterly level for earnings and employment.

so in each quarter, they take the total earnings, and divide by the total employment for that quarter. I want to create an ‘implied’ annual average earnings from this. A few questions:

1. would it be invalid to just take the average of the average quarterly earnings, and multiply that by 4?

2. alternatively, since I can obtain the denominator for each quarter, I wished to do the following:
for each quarter q, multiply average quarterly earnings by the total employment in that quarter. this should yield the total quarterly earnings.
Do this for each quarter, and then add each to get the total annual earnings. divide by the total annual employment.

is 2. equivalent to a ‘weighted’ mean? or can it be directly interpreted as an annual average earnings? my concern is that since each measurement is calculated independently each quarter, the denominator and the numerator could be double counting many jobs.

Answer to Q1: While imperfect, that approach is preferable out of the two you've presented here. Your 'implied' annual average will generally be higher than the actual annual average, with the extent of this error rising with employment churn. Consider calling the result the "quarterly earnings per employment, averaged for the year" or similar, so that your figure isn't misconstrued as annual earnings per employment. Or, if you have the time and inclination, you could report something more sophisticated than a ratio; consider an Autocorrelated Error Model, e.g. Chapter 16 of Griffiths et al, below.

Answer to Q2: This is often done when the data points are independent; the established techniques of “ratio estimation” are covered in, for example, Section 7.4 of John Rice’s textbook (below). However, your data aren't independent. You have four highly dependent readings of a two-dimensional signal (one dimension is earnings, one is employment). You’re quite right to be concerned about what you call double counting, for this particular problem.

Good luck!

References:

Answered by Mark Ebden on January 3, 2022

## Related Questions

### How to interpret “quantile residuals”

1  Asked on December 20, 2021

### Is the regressor (sometimes called “independent” variable) actually independent of the response from a probabilistic perspective?

1  Asked on December 20, 2021 by 24n8

### Laplace approximation in high-dimensions

2  Asked on December 20, 2021 by dionysis-m

### Extremely basic question: how are data assumed to be generated in machine learning?

0  Asked on December 20, 2021 by frass

### Is it appropriated to use an ‘Invariant’ variable in multivariate test?

0  Asked on December 20, 2021 by terauser

### Equation for weighted average with normalization(?)

0  Asked on December 20, 2021

### guessing a number between 1 and 100

1  Asked on December 20, 2021 by dynamic89

### Normalizing posterior distribution

1  Asked on December 20, 2021

### chi squared test in python libraries

1  Asked on December 20, 2021 by eurohacker

### Structural break test for non-stationary time series

0  Asked on December 20, 2021

### How to test for multicollinearity among dummy explanatory variables?

1  Asked on December 18, 2021 by kellyyang

### A routine to choose eps and minPts for DBSCAN

3  Asked on December 18, 2021 by mehraban

### Mixture of Gaussians on Log of Data

2  Asked on December 18, 2021 by zhubarb

### Profile likelihood

1  Asked on December 18, 2021 by denby47

### Johansen cointegration testing: rejecting at 10% vs. 1% level

2  Asked on December 18, 2021

### Retrieving time series from a smoothed periodogram

1  Asked on December 18, 2021 by bayesisbaye

### Which likelihood function is used in linear regression?

3  Asked on December 18, 2021 by floyd

### Distributions of Quadratic form of a normal random variable

1  Asked on December 18, 2021 by xorion-1997

### Euclidean distance from zero

0  Asked on December 18, 2021

### Inconsistent results from partial Mantel test on (non)distance matrices

0  Asked on December 18, 2021 by ian-lane